AI-ready Data Management Practices:

Alaska Ice Seals and Harbor Seals

Stacie Koslovsky

2024-05-17

Polar Ecosystems Program

  • NOAA Fisheries - Alaska Fisheries Science Center

  • Harbor seals and 4 species of ice-associated seals

  • Abundance and distribution of all species

Overview of Image Data Streams

  • Ice Seal Surveys

  • Glacial Harbor Seal Surveys

  • Coastal (terrestrial) Harbor Seal Surveys

KAMERA System

Ice Seal Surveys

  • Use in-flight KAMERA system to collect infrared, RGB, and UV imagery.

  • Use detection model to find hotspots in the thermal imagery.

  • Currently, manually review all thermal hotspots for species identification, but the development/evaluation of a color classification model is underway.

Glacial Harbor Seal Surveys

  • Use in-flight KAMERA system to collect infrared and RGB imagery.

  • For lower-altitude surveys, use detection model to find hotspots in the thermal imagery (using thermal model developed for ice-associated seals). Review color imagery to classify harbor seals.

  • For higher-altitude surveys, data are . Use suppression and ignore zones to indicate areas of overlap. Manually review all images and annotate all seals. Duplicates are flagged during post-processing.

Coastal Harbor Seal Surveys

Collect oblique imagery in-flight using digital SLR camera.

Data are ingested into DB, reviewed to identify which images should be counted. Images that are not selected for counting are either labeled “do not use - contains seals” or “do not use - no seals” to differentiate background imagery from frames that are just not being used for counting.

Once images are selected, run R code to generate image lists for selected images and seals (and ignore zones) are annotates using Kitware’s DIVE software.

AI-Ready Data Efforts

  • Store standardized outputs from each project schema as queries (not all data were collected/processed the same way over the years, so this gives us equivalent data structures to work with)

  • Track how images are/were used (manual review, training, test, validation)

  • Consistent annotation labeling for ease of cross-project training (for staff), annotating

  • Store image names, network paths and image-information data in DB structure - allows for ad hoc queries

  • Develop functions in pepDataConnect R package for generating image lists and/or annotation files for use in DIVE

Thank you!